National Repository of Grey Literature 227 records found  1 - 10nextend  jump to record: Search took 0.01 seconds. 
Neural Network Based Image Modifications
Maslowski, Petr ; Zbořil, František (referee) ; Šůstek, Martin (advisor)
This thesis deals with image colorization and image super-resolution using neural networks. It briefly explains neural networks principles and summarizes current approaches in this domain. It also describes the design, implementation and training of various neural network architectures. The best implemented architecture can colorize images, in particular, works well with outdoor areas. The architecture for image super-resolution with residual blocks that was trained with a perceptual loss function performs a double increase in image resolution (4x more pixels in total). Part of this thesis is also an implementation of a web application that uses trained models for image modification.
Algorithms for Tafl Games
Halmo, Kryštof ; Kočí, Radek (referee) ; Zbořil, František (advisor)
The goal for this work is to create a program witch allows the possibility to play some types of Tafle games against a some algorithms or against a other player. Algorithms used in the solution wear MCTS, Alfabeta and Minmax whit heurystyks which help to find a move faster and evaluate the game board whit specified parameters. Created solution allows the user to select the parameters for running this program. Results of this work provides a comparison between different types of Tafle games and the comparison of different types of algorithms agents one another.
Design of Grammar and User Interface for Visualization and Filtration of Spatio-Temporal Data of Road-Users
Hauerland, Richard ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
Objective of this thesis is about design of grammar and user interface for filtering and visualization of spatiotemporal data. The initial task is to get acquainted with evaluation of traffic data based on trajectory analysis. The next part is the design and description of a formalism which allows spatial filtering and filtering based on static and dynamic attributes. Based on the created formalism, data analysis application with a user interface is designed. Design process was preceded by a comparison of existing solutions. Application is implemented in Qt Framework using C++ and QML languages.
Tool for Piano Practising
Ustinov, Nikita ; Hrubý, Martin (referee) ; Zbořil, František (advisor)
The purpose of this work is to design and implement an application for piano practice. The main disadvantage of existing applications is the limited selection of songs that can be practiced. The application, which is the result of this work, will solve the problem - the user will be able to upload to the application any piano record he wants to practice, and the application will take care of creating a training process. The training process consists of showing the user a certain way of editing notes and simultaneously controlling what the user is playing with a microphone. The biggest challenge of the diploma thesis was to find a way to accurately and quickly classify the audio signal from the microphone. This problem was solved using two independent neural networks with different architectures, which were trained on different data sets. To justify the chosen solution, all the necessary theoretical musical and scientific concepts and methods that are directly related to it will be presented. The resulting application will be tested in next respects: accuracy, speed, noise resistance and the usability of the user.
Active Learning for Processing of Archive Sources
Hříbek, David ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
This work deals with the creation of a system that allows uploading and annotating scans of historical documents and subsequent active learning of models for character recognition (OCR) on available annotations (marked lines and their transcripts). The work describes the process, classifies the techniques and presents an existing system for character recognition. Above all, emphasis is placed on machine learning methods. Furthermore, the methods of active learning are explained and a method of active learning of available OCR models from annotated scans is proposed. The rest of the work deals with a system design, implementation, available datasets, evaluation of self-created OCR model and testing of the entire system.
Cooperation of Multiagent Group in Dynamic Environment
Balajka, Pavel ; Uhlíř, Václav (referee) ; Zbořil, František (advisor)
The thesis summarises thorough analysis of rules and mechanisms of Multiagent Contest for year 2020 followed by design of multiagent group which will try to succeed in a simulation of the mentioned contest with the best results. The design was created according to the Prometheus metodology from general view (scenarios, goals) to specific details (agent plans, messages). Implementation is realized through JaCaMo system, which is also briefly described in this paper. Then the pros and cons of JaCaMo system are analyzed. Lastly the implemented solution of this work is compared with other teams that participated in the mentioned agent competition this year.
Comparison of Cloud Systems for Smart Home
Sobol, Patrik ; Zbořil, František (referee) ; Janoušek, Vladimír (advisor)
This thesis deals with comparison of the biggest cloud computing platforms, Amazon and Google, with high interest in services focused on smart home. It examines connection of services between each other and it summarises options of data transport between device and cloud using protocol MQTT. By integrating of cloud services dashboard is created, which allows to control devices in household.
Support for Playing Board Games Demonstration on Mobile Platforms
Široký, Ondřej ; Kočí, Radek (referee) ; Zbořil, František (advisor)
The aim of this bachelor's thesis is to create a mobile application for the Android platform that will help the player determine the best possible move from  the captured image. The application identifies the game and extracts its current state by using OpenCV library functions. This information is then displayed to the user, who has the ability to manually adjust the game status if the game board is inaccurately read. Subsequently, the application uses the Minimax algorithm with Alpha-beta pruning to determine the best move and displays it to the user.
Rubix Cube Demonstration on Mobile Platforms
Gajdoš, David ; Zbořil, František (referee) ; Zbořil, František (advisor)
This thesis describes three Rubik's cube like puzzles. The goal is to create Android application which allows users to scan sides of a puzzle. After successfully scanning all sides of a puzzle, the application finds sequence of moves needed to perform to solve the puzzle.This found sequence is then textually and visually presented to the user. The application then guides the user through individual moves until the puzzle is solved.
An Application for Tracking of Alcohol in Blood
Nácar, Arthur ; Zbořil, František (referee) ; Hrubý, Martin (advisor)
The aim of this thesis was to create mobile applications for iOS devices and a smartwatches with WatchOS that allows the user to monitor blood alcohol content over time.  The application is implemented in Swift language and it uses Apple HealthKit framework to access the user's personal data. Predictions of blood ethanol content are calculated using a simulation model that takes into account the resorption phase of ethanol and uses the extended Widmark method to estimate the course of the elimination phase.  The result of this work is an application that provides the user with information about the time needed to get a sober and detailed overview of the course of blood alcohol concentration using several available metrics.

National Repository of Grey Literature : 227 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.